© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89483
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and specific regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ious
    -0.06
    isFunction
    -0.06
     ↵
    -0.06
    321
    -0.05
    hb
    -0.05
    MBER
    -0.05
    $MESS
    -0.05
     etc
    -0.05
     th
    -0.05
     ãĤŃ
    -0.05
    POSITIVE LOGITS
    eyse
    0.08
     Už
    0.07
    _Il
    0.07
    ADX
    0.07
    estro
    0.07
    venue
    0.07
    aida
    0.07
    анÑģи
    0.07
    ccoli
    0.07
    ÑĢаÑĩ
    0.07
    Activations Density 0.040%

    No Known Activations